Text parsing of a complex genre
- A text parsing component designed to be part of a system that assists students in academic reading an writing is presented. The parser can automatically add a relational discourse structure annotation to a scientific article that a user wants to explore. The discourse structure employed is defined in an XML format and is based the Rhetorical Structure Theory. The architecture of the parser comprises pre-processing components which provide an input text with XML annotations on different linguistic and structural layers. In the first version these are syntactic tagging, lexical discourse marker tagging, logical document structure, and segmentation into elementary discourse segments. The algorithm is based on the shift-reduce parser by Marcu (2000) and is controlled by reduce operations that are constrained by linguistic conditions derived from an XML-encoded discourse marker lexicon. The constraints are formulated over multiple annotation layers of the same text.
Author: | Harald LüngenGND, Maja Baerenfaenger, Mirco Hilbert, Henning LobinGND, Csilla Puskás |
---|---|
URN: | urn:nbn:de:bsz:mh39-84 |
URL: | http://www.uni-giessen.de/germanistik/ascl/dfg-projekt/pdfs/242_elpub2006.published-version.pdf |
ISBN: | 978-954-16-0040-5 |
Parent Title (English): | ELPUB 2006. Digital Spectrum: Integrating Technology and Culture - Proceedings of the 10th International Conference on Electronic Publishing held in Bansko. ELPUB 2006, Bansko, Bulgaria, June 14-16 |
Publisher: | Foi-Commerce |
Place of publication: | Sofia |
Editor: | Milena Dobreva, Bob Martens |
Document Type: | Conference Proceeding |
Language: | English |
Year of first Publication: | 2006 |
Tag: | XML applications; discourse parsing; rhetorical structure; text parsing |
GND Keyword: | Textanalyse ; Diskursanalyse ; Computerlinguistik |
Page Number: | 10 |
First Page: | 247 |
Last Page: | 256 |
DDC classes: | 400 Sprache / 410 Linguistik / 410 Linguistik |
Open Access?: | ja |
Linguistics-Classification: | Computerlinguistik |
Licence (German): | Urheberrechtlich geschützt |